{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2312.11805","title":"Gemini: A Family of Highly Capable Multimodal Models","created":"2023-12-19","cited_by_count":872},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95},{"id":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83},{"id":"2404.02668","title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","created":"2024-04-03","cited_by_count":81},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64},{"id":"2209.01206","title":"Transformers in Remote Sensing: A Survey","created":"2022-09-02","cited_by_count":61},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41},{"id":"2011.03247","title":"Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery","created":"2020-11-06","cited_by_count":33},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32},{"id":"2312.16202","title":"Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection","created":"2023-12-23","cited_by_count":27},{"id":"2409.08582","title":"ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning","created":"2024-09-13","cited_by_count":23},{"id":"2407.14032","title":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","created":"2024-07-19","cited_by_count":17},{"id":"2409.12612","title":"Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning","created":"2024-09-19","cited_by_count":16},{"id":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15},{"id":"2310.04698","title":"Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis","created":"2023-10-07","cited_by_count":14},{"id":"2411.11360","title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","created":"2024-11-18","cited_by_count":13},{"id":"2401.04125","title":"DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling","created":"2024-01-04","cited_by_count":12},{"id":"2406.10828","title":"PyramidMamba: Rethinking Pyramid Feature Fusion with Selective Space State Model for Semantic Segmentation of Remote Sensing Imagery","created":"2024-06-16","cited_by_count":12},{"id":"2405.20810","title":"Context-aware Difference Distilling for Multi-change Captioning","created":"2024-05-31","cited_by_count":10},{"id":"2205.12410","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-05-24","cited_by_count":7},{"id":"2410.10047","title":"ChangeMinds: Multi-task Framework for Detecting and Describing Changes in Remote Sensing","created":"2024-10-13","cited_by_count":7},{"id":"2411.07688","title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","created":"2024-11-12","cited_by_count":6},{"id":"2406.13424","title":"Towards a multimodal framework for remote sensing image change retrieval and captioning","created":"2024-06-19","cited_by_count":5},{"id":"2407.09548","title":"Towards Temporal Change Explanations from Bi-Temporal Satellite Images","created":"2024-06-27","cited_by_count":3},{"id":"2410.23946","title":"MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption","created":"2024-10-31","cited_by_count":3},{"id":"2405.12875","title":"Diffusion-RSCC: Diffusion Probabilistic Model for Change Captioning in Remote Sensing Images","created":"2024-05-21","cited_by_count":2}],"next_cursor":null}